Intelligent ship navigation risk evaluation energy field modeling method fusing multi-ship interaction characteristics

Abstract

The invention provides an intelligent ship navigation risk evaluation energy field modeling method fusing multi-ship interaction characteristics, and the method comprises the steps: obtaining ship AIS data, and extracting the longitude and latitude and course information of ships in the ship AIS data; quantifying ship traffic complexity, including density complexity, approaching complexity and defibering complexity; quantitatively describing the traffic complexity between the two ships according to the density complexity, the approaching complexity and the defibering complexity, and expanding the traffic complexity to reflect the traffic complexity of multi-ship interaction characteristics; designing a navigation energy field model reflecting multi-ship interaction characteristics according to the traffic complexity; the navigation scene is graded in combination with an ALARP criterion; and determining a quantitative basis for adaptive switching of the operation modes of the intelligent ship. According to the method, the risk evolution rule of ship group behaviors in a complex traffic environment can be deeply revealed, theoretical support and algorithm basis are provided for self-adaptive switching of operation modes of the intelligent ship, and practical application of the intelligent ship in the aspects of autonomous cognition, risk evaluation and the like is promoted.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of maritime traffic management, in particular, especially relates to an intelligent ship navigation risk evaluation energy field modeling method fusing multi-ship interaction features. BACKGROUND

[0002] In the actual maritime navigation process, intelligent ships are disturbed by various dynamic environmental factors, especially in complex scenes such as multi-ship intersection and high-density traffic flow, how to effectively evaluate the navigation environment and identify potential risks has become an important challenge to ensure the safe navigation of intelligent ships. However, there is still a significant gap in the existing research in the evaluation of navigation scenes, and there is a lack of a quantitative evaluation model that can dynamically reflect the complexity of the current navigation environment of intelligent ships, especially in typical high-complexity navigation scenes such as multi-ship intersection and high-density traffic flow. The traditional risk warning system is difficult to effectively capture the interaction between ships and the spatio-temporal evolution characteristics of potential risk areas, which limits the understanding of intelligent ships to environmental changes and weakens their ability to adaptively switch between different operation modes. SUMMARY

[0003] In view of the technical problems of the prior art that intelligent ships lack effective navigation risk evaluation mechanism in complex maritime traffic environment, an intelligent ship navigation risk evaluation energy field modeling method fusing multi-ship interaction features is provided. The present application can dynamically quantify the complexity of the traffic scene and identify potential high-risk areas to provide a quantitative basis for the adaptive switching of intelligent ship operation modes.

[0004] The technical means adopted by the present application are as follows: An intelligent ship navigation risk evaluation energy field modeling method fusing multi-ship interaction features, comprising: S1, acquiring ship AIS data and extracting the latitude, longitude and heading information of the ship in the ship AIS data; S2, quantifying the ship traffic complexity, including quantifying the density complexity, approaching complexity and dispersion complexity in the traffic environment; S3, quantitatively describing the traffic complexity between two ships according to the density complexity, approaching complexity and dispersion complexity, and extending the traffic complexity between two ships to traffic complexity reflecting multi-ship interaction features; S4, designing a navigation energy field model reflecting multi-ship interaction features according to the traffic complexity; S5, classifying the navigation scene in combination with the ALARP criterion; S6, determining the quantitative basis for adaptive switching of intelligent ship operation modes.

[0005] Further, step S2 specifically comprises: S21, calculating the density complexity, the calculation formula is as follows:

[0006] In the above formula, denotes the density complexity, denotes a correction parameter dependent on the ship's sailing environment, the value of which depends on the ship type and sailing environment, denotes the relative distance between the two ships at time t, , and are the latitude and longitude of the ship , and are the latitude and longitude of the ship ; S22, calculating the imminent complexity, the calculation formula is as follows:

[0007] In the above formula, denotes the imminent complexity, denotes an adjustment factor, denotes a spatial convergence factor, denotes a temporal convergence factor, denotes the ship safety distance, wherein:

[0008]

[0009] In the above formula, and denote the speed of the ship and the ship at time t, and denote the heading of the ship and the ship at time t, , ;

[0010] The ship safety distance is calculated by a potential collision risk domain (PRSD) model, the shape of the ship domain is an eccentric ellipse, and the safety boundary of the ship is specifically as follows:

[0011] In the above formula, denotes the forward boundary of SD, Indicates the backward boundary of SD. This represents the angle between point p and the bow direction. Indicates the length of the ship. This indicates the lateral influence parameter of SD. The parameter representing the longitudinal influence of SD. Indicates the potential collision risk index; S23. Calculate the complexity of the scrambling process, using the following formula:

[0012] In the above formula, This indicates the complexity of the solution.

[0013] Further, step S3 specifically includes: S31. Based on the density complexity, approximation complexity, and unwinding complexity, the traffic complexity between the two ships is quantitatively described as follows:

[0014] In the above formula, Indicates the traffic complexity between two ships. Indicate density complexity, Indicates approximation complexity. Indicates the complexity of the solution; S32. Constructing the traffic complexity matrix in multi-ship interaction scenarios. As shown in the following formula:

[0015] In the above formula, express The number of all vessels in the waterway at any given time; S33, Computational Complexity Matrix The weight matrix is ​​shown in the following formula:

[0016] In the above formula, Representing the complexity matrix The weight matrix; S34. The complexity matrix A Performing the Hadamard product with the weight matrix yields... t The overall complexity of each ship's traffic situation at any given time is shown in the following formula: .

[0017] Furthermore, in step S4, the risk function of the navigation energy field model is shown in the following equation:

[0018] in the above formula, denotes the distance from the center of the ship, denotes the calculated ship traffic complexity, n denotes the number of ships perceived in the navigation scene, denotes the adjustment parameter.

[0019] Further, in step S5, the risk value calculated by the navigation energy field is divided into four level regions, which are: negligible region (0%-50%), ALARP lower limit region (50%-70%), ALARP upper limit region (70%-90%) and unacceptable region (90%-100%).

[0020] Further, in step S6, the scene levels divided by the ALARP criterion are respectively mapped with the intelligent ship operation mode, including: The ALARP negligible region corresponds to a scene with low navigation safety risk, and no additional intervention is required, so the recommended operation mode is autonomous; the ALARP lower limit region corresponds to a remote control mode; the ALARP upper limit region corresponds to a personnel on-board operation mode; and the ALARP unacceptable region corresponds to an emergency response mode.

[0021] Compared with the prior art, the present application has the following advantages: 1. The intelligent ship navigation risk evaluation energy field modeling method fusing multi-ship interaction characteristics provided by the present application comprehensively quantifies the interaction risk between ships from three dimensions of density complexity, imminent complexity and dispersion complexity, based on the traffic complexity measurement method of the ship intrinsic property and the potential collision risk ship domain (PRSD) theory, thereby effectively improving the risk perception ability of the intelligent ship in complex scenes such as multi-ship intersection and dense traffic.

[0022] 2. The intelligent ship navigation risk evaluation energy field modeling method fusing multi-ship interaction characteristics provided by the present application, in view of the deficiency of ignoring the multi-ship dynamic coupling characteristics in the traditional energy field model, introduces a ship interaction mechanism to establish a navigation energy field model that can reflect the mutual influence relationship between ships. The model can dynamically depict the spatio-temporal evolution trend of the risk area, significantly enhancing the modeling accuracy and adaptability of the energy field method in complex traffic environments.

[0023] 3. The intelligent ship navigation risk evaluation energy field modeling method fusing multi-ship interaction characteristics provided by the present application, in combination with the ALARP risk tolerance criterion, establishes a scene grading mechanism based on the risk level, and accordingly proposes a quantitative basis for adaptive switching of the intelligent ship operation mode, providing scientific support for the dynamic switching of the intelligent ship between multiple operation modes, and improving the safety guarantee ability and operation stability of the intelligent ship in high dynamic environments.

[0024] Based on the above reasons, the present application can be widely used in the field of marine vessel traffic, etc. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor under the premise of the drawings.

[0026] Figure 1 The flow chart of the method of the present application.

[0027] Figure 2 The distribution map of the vessel provided by the embodiment of the present application.

[0028] Figure 3 The vessel traffic complexity calculation result provided by the embodiment of the present application.

[0029] Figure 4 The sailing energy field model schematic diagram provided by the embodiment of the present application.

[0030] Figure 5 The simulation trajectory generated by the sailing energy field model provided by the embodiment of the present application.

[0031] Figure 6 The four level regions of the risk value division provided by the embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the person skilled in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0034] like Figure 1 As shown, this invention provides an energy field modeling method for intelligent ship navigation risk assessment that integrates multi-ship interaction features, including: S1. Obtain ship AIS data and extract the ship's latitude, longitude, and heading information from the ship AIS data; the ship distribution map is shown below. Figure 2 As shown; S2. Quantify the complexity of ship traffic, including the density complexity, proximity complexity, and de-escalation complexity in the traffic environment; S3. Based on the density complexity, approximation complexity and relief complexity, quantitatively describe the traffic complexity between two ships, and extend the traffic complexity between two ships to the traffic complexity that reflects the interaction characteristics of multiple ships. S4. Based on the traffic complexity, design a navigation energy field model that reflects the interaction characteristics of multiple ships; S5. Classify navigation scenarios based on the ALARP criterion; S6. Determine the quantitative basis for the adaptive switching of intelligent ship operation modes.

[0035] In a specific implementation, as a preferred embodiment of the present invention, step S2 specifically includes: S21. Calculate the density complexity using the following formula:

[0036] In the above formula, Indicate density complexity, This indicates a correction parameter dependent on the ship's navigation environment, with a value of 1.81. The value depends on the ship type and navigation environment, and is typically 30. express The relative distance between the two ships at any given time, , and For ships latitude and longitude and the latitude and longitude of the ship ; S22, calculating the approaching complexity, the calculation formula is as follows:

[0037] In the above formula, represents the approaching complexity, represents the adjustment factor, and the value is 2, represents the spatial convergence factor, represents the time convergence factor, represents the ship safety distance, wherein:

[0038]

[0039] In the above formula, and represent the speed of the ship and the ship at the moment, and represent the heading of the ship and the ship at the moment, , ;

[0040] The ship safety distance is calculated by the potential collision risk domain (PRSD) model, the shape of the ship domain is an eccentric ellipse, and the safety boundary of the ship is specifically as follows:

[0041] In the above formula, represents the forward boundary of the SD, represents the backward boundary of the SD, represents the included angle between the point p and the bow direction, represents the length of the ship, represents the transverse influence parameter of the SD, represents the longitudinal influence parameter of the SD, represents the potential collision risk index; S23, calculating the approaching complexity, the calculation formula is as follows:

[0042] In the above formula, The density complexity is represented. The calculation result is shown in the following table. Figure 3

[0043] In the implementation, as a preferred embodiment of the present application, step S3 specifically includes: S31, according to the density complexity, the approaching complexity and the dispersion complexity, quantitatively describing the traffic complexity between two ships, as shown in the following formula:

[0044] In the above formula, represents the traffic complexity between two ships, represents the density complexity, represents the approaching complexity, represents the dispersion complexity; S32, constructing a traffic complexity matrix in a multi-ship interaction scenario , as shown in the following formula:

[0045] In the above formula, represents the number of all ships in the water area at the moment; S33, calculating the weight matrix of the complexity matrix , as shown in the following formula:

[0046] In the above formula, represents the weight matrix of the complexity matrix ; S34, performing Hadamard product operation on the complexity matrix A and the weight matrix, obtaining the comprehensive complexity of each ship in the traffic situation at the moment t , as shown in the following formula: .

[0047] In the implementation, as a preferred embodiment of the present application, in step S4, according to the traffic complexity, a sailing energy field model reflecting the multi-ship interaction characteristics is designed, as shown in the following formula: Figure 4 , and a segment of simulation trajectory is generated for calculating the risk, as shown in the following formula: Figure 5 . The risk function of the sailing energy field model is shown in the following formula:

[0048] In the above formula, represents the distance from the center of the ship, represents the calculated traffic complexity of the ship, n represents the number of ships perceived in the sailing scenario,​ represents a regulation parameter, and takes a value of 0.1.

[0049] In a specific implementation, as a preferred embodiment of the present application, in step S5, the risk value calculated by the navigation energy field is divided into four level regions, respectively: ALARP negligible region (0%-50%), ALARP lower limit region (50%-70%), ALARP upper limit region (70%-90%), and ALARP unacceptable region (90%-100%), as shown in the following table. Figure 6

[0050] In a specific implementation, as a preferred embodiment of the present application, in step S6, the scene levels divided by the ALARP criterion are respectively mapped with the intelligent ship operation modes, including: The ALARP negligible region corresponds to a scene with a relatively low navigation safety risk, and no additional intervention is needed, so the recommended operation mode is autonomous; the ALARP lower limit region corresponds to a remote control mode; the ALARP upper limit region corresponds to a mode of in-ship personnel operation; and the ALARP unacceptable region corresponds to an emergency response mode.

[0051] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.​

Claims

1. A method for modeling an intelligent ship navigation risk evaluation energy field by fusing multi-ship interaction features, characterized in that, The method comprises the following steps: S1, acquiring ship AIS data, and extracting the longitude and latitude and heading information of the ship from the ship AIS data; S2, quantifying the traffic complexity of the ship, including quantifying the density complexity, the approaching complexity and the dispersing complexity in the traffic environment; S3, quantitatively describing the traffic complexity between two ships according to the density complexity, the approaching complexity and the dispersing complexity, and extending the traffic complexity between two ships to the traffic complexity reflecting the interaction characteristics of multiple ships; S4, designing a navigation energy field model reflecting the interaction characteristics of multiple ships according to the traffic complexity; S5, classifying the navigation scene in combination with the ALARP criterion; S6, determining the quantitative basis for adaptive switching of the intelligent ship operation mode. 2.The intelligent ship navigation risk assessment energy field modeling method with fusion of ship interaction features according to claim 1, characterized in that, Step S2 specifically comprises: S21, calculating the density complexity, and the calculation formula is as follows: in the above formulae, denotes the density complexity, denotes a correction parameter depending on the ship's sailing environment, the value of depends on the ship type and the sailing environment, denotes the relative distance between the two ships at the time instant, , and are the latitude and longitude of the ship , and are the latitude and longitude of the ship . S22, calculating the approaching complexity, and the calculation formula is as follows: In the above formulae, denotes the imminent complexity, denotes the adjustment factor, denotes the spatial convergence factor, denotes the temporal convergence factor, denotes the ship safety distance, wherein: In the above formulae, and denote the speed of the ship and the ship at the time instant t, and denote the heading of the ship and the ship at the time instant t, , ; Vessel safety distance The shape of the vessel field is an eccentric ellipse calculated from the potential collision risk field model, the vessel safety boundary is given by the following equation: In the above formulae, denotes the forward boundary of the SD, denotes the backward boundary of the SD, denotes the included angle between the point p and the heading of the ship, denotes the length of the ship, denotes the transverse influence parameter of the SD, denotes the longitudinal influence parameter of the SD, denotes the potential collision risk index; S23, calculating the dispersing complexity, and the calculation formula is as follows: In the above formula, denotes the disentanglement complexity. 3.The intelligent ship navigation risk assessment energy field modeling method of fusing multi-ship interaction features according to claim 1, characterized in that, Step S3 specifically comprises: S31, quantitatively describing the traffic complexity between two ships according to the density complexity, the approaching complexity and the dispersing complexity, as shown in the following formula: In the above formulae, represents the traffic complexity between two vessels, represents the density complexity, represents the proximity complexity, represents the spread-out complexity; S32, construct a traffic complexity matrix under a multi-ship interaction scenario as shown in the following formula: In the above formula, denotes the number of all ships in the water area at the time S33, calculating a complexity matrix weight matrix of the following formula: In the above formula, denotes a weight matrix of the complexity matrix denotes a weight matrix of the complexity matrix S34, the complexity matrix A S34= S33* W, (8) t The complexity of each ship in the traffic situation at time t is shown as follows: 。 4. The intelligent ship navigation risk assessment energy field modeling method of claim 1, wherein, In step S4, the risk function of the navigation energy field model is as shown in the following formula: In the above formulae, denotes the distance to the center of the ship, denotes the calculated ship traffic complexity, n denotes the number of ships perceived in the sailing scenario, denotes the adjustment parameter.

5. The intelligent ship navigation risk assessment energy field modeling method of claim 1, wherein, In step S5, the risk value calculated by the navigation energy field is divided into four level regions, which are ALARP negligible region, ALARP lower limit region, ALARP upper limit region and ALARP unacceptable region.

6. The intelligent ship navigation risk assessment energy field modeling method of fusing multi-ship interaction features according to claim 1, characterized in that, In step S6, the scene levels divided by the ALARP criterion are respectively mapped with the intelligent ship operation mode, including: The ALARP negligible region corresponds to a scene with low navigation safety risk, and no additional intervention is required, so the recommended operation mode is autonomous; the ALARP lower limit region corresponds to a remote control mode; the ALARP upper limit region corresponds to a ship personnel operation mode; and the ALARP unacceptable region corresponds to an emergency response mode.

Images